Distillation and model compression · MLD-0083
AWQ
A weight-quantization approach using activation information to protect important weight channels.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Quantize an instruction model for inference.
Original caveat
Hardware-compatible implementation determines speed benefits.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · SLM · LLM.
Aliases: Activation-aware weight quantization.
Related concepts
Original references
- Distilling the Knowledge in a Neural Network ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- PEFT: quantization guide ↗ · Consulted
- Original reference URL ↗